© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57366
    Prev
    Next
    INDEX
    Explanations

    afisha

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    磶
    -0.10
    од
    -0.09
    à¹Į
    -0.09
    ä¸įå®ļ
    -0.09
    fly
    -0.09
    åıijåħī
    -0.09
    åħļç»Ħ
    -0.08
    çĪ·
    -0.08
    天涯
    -0.08
    鸷
    -0.08
    POSITIVE LOGITS
    istani
    0.10
    rikes
    0.10
    raid
    0.09
    ainted
    0.09
    roud
    0.09
    GPC
    0.09
    åıĪ被
    0.09
    _INET
    0.09
    -American
    0.08
    adm
    0.08
    Activations Density 0.029%

    No Known Activations